Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ny
    -0.07
     hid
    -0.06
    _iter
    -0.06
     fantasy
    -0.06
    ombok
    -0.06
    akest
    -0.06
    Removed
    -0.06
    -largest
    -0.06
     handmade
    -0.06
    .closed
    -0.06
    POSITIVE LOGITS
    ĩa
    0.07
    fm
    0.07
    аров
    0.06
     QQ
    0.06
    .LOC
    0.06
    жив
    0.06
     deficient
    0.06
    _pi
    0.06
     Gül
    0.06
    Typ
    0.06
    Act Density 0.004%

    No Known Activations